Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    _E

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     begin
    -0.07
    �
    -0.07
    ift
    -0.07
    귓
    -0.07
     destin
    -0.07
    	task
    -0.07
    .features
    -0.07
     señal
    -0.07
    ink
    -0.07
    مسؤول
    -0.07
    POSITIVE LOGITS
    uitive
    0.07
    평
    0.07
    淮
    0.07
     diagnostics
    0.07
     intrusive
    0.07
     confirmation
    0.07
    /memory
    0.07
    forcer
    0.07
    ?;↵
    0.07
    getMethod
    0.07
    Act Density 0.038%

    No Known Activations